fleet runs on your own machine — the client starts it, so there is no endpoint to ping. 649 installs a week from pypi. Last commit 13 Oct 2026.
Every machine you have, for your coding agent: live GPU, VRAM, RAM and disk, and SSH.
What the code does
We read the source, 2 d ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
[ -f /.dockerenv ] && is_container=1
proc = subprocess.Popen([_fleet(), *args], stdout=subprocess.PIPE,
return yaml.load(text, Loader=_Loader)
FLEET_KEY = CONFIG_DIR / "id_ed25519"
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add fleet -- uvx agents-fleet{
"mcpServers": {
"fleet": {
"args": [
"agents-fleet"
],
"command": "uvx"
}
}
}[mcp_servers.fleet]
command = "uvx"
args = ["agents-fleet"]{
"mcpServers": {
"fleet": {
"args": [
"agents-fleet"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"fleet": {
"args": [
"agents-fleet"
],
"command": "uvx"
}
}
}Alternatives to fleet
same job, measured the same wayCode review on your own machine, for you and your coding agent. Nothing leaves your computer.
See what every AI agent is doing and what's waiting on you: one to-do list for agents and your team
Local video studio for your coding agent: scenes, voice, music and captions, on your machine.
Team memory for coding agents: rules you approve, served to every agent, and which ones it cited.
Every project you have going, on one board your coding agents keep current and you actually read.
Let your coding agent manage real todos, events, and check-in habits in Kenotex on your Mac.
Drive the Godot engine from an AI coding agent: build, run, play, and verify your game live.
Local-first long-term memory for AI coding agents. Stored on your own machine.
fleet — questions
Answers built from our own checks of this server.